Rierino launches AI agent builder to power agents with full system awareness
Rierino, the next-generation low-code platform for enterprise innovation, announced today the launch of AI Agent Builder —a new capability designed to help organizations build and deploy intelligent agents that operate inside real systems, not just across conversations.
Unlike traditional approaches that focus on prompts or pre-scripted flows, Rierino's AI Agent Builder allows teams to give agents secure access to backend logic, real-time workflows, and internal APIs—enabling actions like creating a purchase request, retrieving customer history, or triggering multi-step automation based on enterprise data.
'The missing piece in AI agent development isn't more intelligence. It's more structure,' said Berkin Ozmen, Co-Founder and CTO of Rierino. 'AI agents will transform the enterprise by executing real actions, governed by real logic—where business value is actually created. That requires infrastructure purpose-built for execution, not just conversation.'
A Foundation for Enterprise-Grade Agents
AI Agent Builder is not a standalone feature, but a natural extension of Rierino's composable, low-code platform. With it, developers can transform any internal logic into agent-accessible capabilities governed by platform-level RBAC, validation rules, audit trails, and contextual schema definitions.
Agents can invoke saga flows, Rierino's real-time, event-driven orchestration components, as native tools with clearly defined inputs and outputs. These flows eliminate the need for custom glue code or fragile integrations and make structured actions accessible to large language models (LLMs) by design.
The platform supports integration with a wide range of LLM providers, including OpenAI, Google Gemini, Amazon Bedrock, Mistral, Anthropic, and on-prem deployments like Ollama or LocalAI—giving enterprises full flexibility over how and where their AI workloads run.
Agents built with Rierino are also channel-agnostic by default. They can be accessed through Rierino's UI, exposed as APIs, or triggered by external events—enabling seamless deployment across chat interfaces, operational systems, or custom frontends.
And because all logic is built using Rierino's microservice-based foundation, agent capabilities are modular, versioned, and reusable across teams and systems—ensuring long-term maintainability and scalability as business needs evolve.
From Prototypes to Production-Grade Agents
Most AI agent platforms today are optimized for experimentation—focused on prototyping flows, generating responses, or showing basic integrations. While that's helpful in the early stages, it falls short in real-world enterprise scenarios where agents must operate across multiple systems, comply with business policies, and deliver measurable outcomes.
Rierino's AI Agent Builder is built for the next phase: production-grade deployment. It enables teams to move beyond pilots and proof-of-concepts by equipping agents with structured tools, secure runtime environments, and composable business logic. Agents aren't just asked to generate ideas—they're expected to pull real-time data, initiate multi-step workflows, and act within enterprise guardrails.
This shift—from conversation to execution—is what turns AI from a novelty into a force multiplier for productivity, automation, and innovation at scale.
Not Just a Tool—An Agent Infrastructure Layer
While many platforms position agents as digital assistants or conversational layers, Rierino takes a fundamentally different approach: Agents are infrastructure-level components that should be embedded, orchestrated, and governed like any other part of a modern enterprise system.
AI Agent Builder is not a new direction—it's the natural evolution of Rierino's long-standing AI focus. As the first low-code platform to offer embedded AI capabilities dating back to 2020, Rierino has consistently pushed beyond surface-level automation. The 2023 launch of RAI, its embedded GenAI assistant, extended these capabilities into content, translation, and UI generation. AI Agent Builder now extends that same architectural depth to autonomous, action-driven agents.
With Rierino, every workflow, API, or rule-based decision can be exposed as a tool an agent can invoke—governed, automatically versioned, and monitored for safe execution. This turns your internal architecture into an AI-ready surface where agents can operate with full trust and transparency.
For organizations looking to scale AI safely and meaningfully, this isn't just another feature—it's a platform-level capability ensuring agents to evolve as systems grow, maintain compliance as policies shift, and deliver real business impact without introducing chaos or risk.
Rierino AI Agent Builder is now available to enterprise teams looking to bring scalable AI execution into their digital ecosystems.
About Rierino
Rierino is a next-generation technology company helping organizations accelerate digital transformation through low-code development, composable architecture, and embedded intelligence. Its platform empowers teams to create scalable microservices, orchestrate business logic, and build intelligent applications—without black-box constraints. Rierino is backed by the Future Impact Fund and was named one of Fast Company's Top 100 Startups to Watch.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Arabian Post
13 hours ago
- Arabian Post
Microsoft Unveils AI Diagnostician Surpassing Human Clinicians
Microsoft has introduced the MAI Diagnostic Orchestrator, an advanced AI system that diagnoses complex medical conditions with four times the accuracy of unaided doctors. In a trial using 304 challenging case studies from the New England Journal of Medicine, the tool achieved an 85.5% success rate, compared with around 20% for physicians barred from referencing external resources. The innovation rests on a multi-agent 'orchestrator' framework that mimics a panel of five specialists, each performing distinct functions—formulating hypotheses, recommending tests, and collating evidence. The system operates using a 'chain‑of‑debate' methodology, requiring its AI components to methodically justify each diagnostic step. When integrated with OpenAI's o3 model, performance peaked; other large language models—Meta, Anthropic, Google and xAI—also saw significant improvements under this architecture. Microsoft's AI health arm, led by Mustafa Suleyman and including deep learning figures formerly from DeepMind, emphasises that the platform is model‑agnostic. Nevertheless, Suleyman described outcomes as 'dramatically better than human performance: faster, cheaper and four times more accurate'. Dominic King, another former DeepMind health researcher now at Microsoft, praised the 'landmark' nature of the work, while cautioning it remains in pre‑clinical phases and has not yet undergone peer review. ADVERTISEMENT The technology not only enhances diagnostic precision but optimises test utilisation, reportedly cutting testing costs by up to 20%. In one illustrative example, MAI‑DxO attained accurate diagnoses with fewer and less expensive investigations. It is anticipated that the system will be rolled into Microsoft's consumer‑facing platforms such as Copilot and Bing, which manage tens of millions of health‑related inquiries daily. Yet the path to clinical integration faces significant hurdles. Experts highlight that the trialistic setting—artificial and devoid of real‑world complexity—differs vastly from live medical environments. Cardiologist Eric Topol of the Scripps Research Translational Institute noted that, while indicative of generative AI's potential, the work 'was not done in the setting of real world medical practice'. Microsoft itself stresses the need for extensive validation before deployment in clinical care. The development also intersects with broader dynamics in AI. As Microsoft seeks to extend its exclusive partnership with OpenAI—investing nearly $14 bn—the tension over platform control is evident. Despite being model‑agnostic, Microsoft's reliance on OpenAI's o3 model for peak performance draws renewed attention to the strategic leverage being negotiated. Alongside the Microsoft leap, other healthcare AI initiatives continue to gain momentum. Google's DeepMind recently launched AlphaGenome, a model targeting non‑coding DNA regions with implications for genetic illness; separately, UK trials report AI detection of epilepsy and other conditions via imaging and health record analysis. These developments underscore a growing shift from theoretical promise to practical application. Microsoft's MAI‑DxO represents a pivotal juncture—not as a medical panacea but as a catalyst in the transformation of diagnostic medicine. Its broader significance lies not only in outperforming unaided clinicians in controlled trials, but in pointing towards a future where AI supports medical professionals in managing complexity and resource constraints.
Martechvibe
19 hours ago
- Martechvibe
Simon Data Launches Composable AI Agents for Marketers
Simon Data, the AI-first composable CDP built for modern marketing teams, has announced the launch of Composable AI Agents for marketers. Simon's Composable AI Agents, built natively on Snowflake Cortex AI and powered by Claude from Anthropic, introduce a new operating model that provides marketers with direct, governed access to explore, identify, and activate data for personalisation without requiring code or relying on data teams. Despite significant investments in analytics resources and marketing clouds with integrated data platforms, most marketers still lack visibility into what data is missing, let alone how to act on it. They lack the insight into subtle behavioural patterns, emotional cues in support conversations, and real-world contextual triggers. Simon's agents help by uncovering data that marketers already have but can't easily access, along with new contextual signals they couldn't reach before. These insights are then put to work instantly across campaigns. This streamlines marketing workflows, closes the gap between planning and doing, and makes it easier to deliver personalised, timely marketing at scale. ALSO READ: 'Marketers have been told for years that personalisation was solved, but the reality has been static segments, brittle workflows, and missed customer moments,' said Jason Davis, CEO and Co-Founder of Simon Data. 'Composable AI Agents shift that reality, giving marketers direct access to context, decisioning, and execution. It's a new foundation for modern marketing that is faster, more insightful, and finally in the marketer's control.' Composable AI Agents are modular, task-specific software components powered by AI. Each one performs a discrete function to automate complex marketing workflows: analysing sentiment, identifying high-intent behaviours, modelling micro-audiences, or triggering personalised campaigns based on real-time context. They can be reused, combined, and adapted to support different goals. This creates a dynamic, AI-powered marketing system that works like a virtual, always-on data and ops team, helping marketers move from insight to execution with minimal lift. Simon's agents run entirely inside the Snowflake environment. That means data, prompts, and activation all happen in place, under full enterprise governance, observability, and control. There's no data movement, no black-box logic, and no compromise on speed or scale. With Composable AI Agents, marketers gain hands-on control over signals and execution logic. Even small teams that once waited weeks for data pulls or SQL queries can now operate with the speed and precision of organisations with far more resources. ALSO READ: 'Past systems weren't built for real-time insight or activation, which made personalisation hard to scale,' said Matt Walker, CTO and Co-Founder at Simon Data. 'Simon has changed that by bringing reasoning, context, and execution directly into the data layer for marketing to use. It's a fundamental technical shift that enables a new operating model.' Simon's implementation demonstrates the benefits of using Snowflake AI Data Cloud architecture to compose a data and AI stack, paired with Anthropic's advanced AI models. Simon's agents align directly with a shared vision for secure, governed AI in the enterprise. 'Simon's implementation of Composable AI Agents is a strong example of what's possible when applications are built natively in the Snowflake AI Data Cloud,' said Jeff Hollan, Head of Cortex AI Agents & Apps, Snowflake. 'By combining real-time data access with the flexibility of Snowflake Cortex, Simon empowers marketers to discover and activate data, while giving data teams confidence that everything runs within their governance and observability frameworks.' Three Types of Composable AI Agents: Insights Agents analyse all customer interactions to find valuable campaign opportunities using Claude's advanced reasoning capabilities Data Agents use AI-generated 'Smart Fields' technology to transform contextual data into actionable customer attributes Automation Agents execute campaigns using this deep contextual understanding, automatically creating and optimising hundreds of adaptive micro-targeted campaigns. Once Simon's Composable AI Agents surface the right signals and create the audience logic, they automate the flow directly into customer engagement platforms, such as Braze, Attentive, Iterable, and others. The output is campaigns enhanced with intelligence far beyond traditional audience segmentation. Rather than pre-scheduled blasts or static journeys, Simon enables message delivery that aligns with the behaviours, sentiment, and context driving each customer's decision. These rapid, high-impact campaigns result in critical business outcomes like winbacks, upsells, cross-sells, and repeat purchases. ALSO READ: Simon Data, Snowflake Partner To Aid Marketers With Data Capabilities The Martechvibe team works with a staff of in-house writers and industry experts. View More
Arabian Post
21 hours ago
- Arabian Post
AI Boosts Research and Creativity Through Human–Machine Synergy
Generative artificial intelligence is revolutionising research and innovation, empowering humans to push the boundaries of creativity and discovery. According to Innovation Endeavors, one in eight workers now engages with AI monthly—90 percent of that growth occurring in the past six months. Tools are reshaping software development by merging programming, design and product planning into unified pipelines. Meta is aggressively competing, launching a 'Superintelligence' research wing, hiring top-tier talent—including three prominent OpenAI researchers and Alexandr Wang of Scale AI—backed by a $14.3 billion investment and lavish compensation to regain dominance amid the rapid turnover of leading AI models. This high-stakes talent scramble highlights both ambition and the volatility inherent to an industry where leadership lasts mere weeks before disruption takes hold. The synergy of human intelligence and AI prowess is being documented across diverse sectors. A ground-breaking study from Thomas P. Kehler and colleagues introduces 'Generative Collective Intelligence', which positions AI as both agent and knowledge manager in collaborative decision-making. When applied to complex challenges—such as climate adaptation and healthcare—GCI can bridge gaps that solitary human or machine efforts cannot. ADVERTISEMENT Complementary research, published by Andrea Gaggioli's team, proposes a framework of extended creativity. By describing AI's role in modes spanning support to full symbiosis, the study offers practical design and ethical guidance for researchers aiming to integrate AI without eclipsing human agency. Concrete outcomes underscore these frameworks. In materials science, for instance, the deployment of AI-driven tools in a major U.S. firm accelerated novel material generation by 44 percent. This resulted in a 39 percent rise in patent filings and a 17 percent increase in prototype development—medium and radical innovation rose noticeably, with overall R&D productivity jumping 13–15 percent. In healthcare settings, Duke University researchers have begun implementing an AI safety and performance assessment system. Preliminary results show AI-based note‑taking tools reduce physician workload—20 percent less time spent writing medical notes and a 30 percent decline in after-hours work. These tools, integrated with systems like Epic, show promise but also highlight the need for ongoing accuracy monitoring. Emerging AI breakthroughs beyond traditional research are being noted. Google's AMIE diagnostic system now outperforms human clinicians across 28 medical evaluation metrics, marking a milestone in clinical AI diagnostics. In biotechnology, Profluent Bio's ProGen3 model family demonstrates 'biology scaling laws,' where increasing model size leads to more accurate and diverse protein sequences—potentially streamlining drug development. On the frontier of cognitive science, studies at MIT, Cornell and Santa Clara universities reveal concerns: essays generated via AI like ChatGPT show reduced originality, cultural narrowing and diminished brain activity in users. Researchers warn against overreliance, pointing to potential long-term costs for creativity and cultural diversity. These findings mirror Aru's neurobiological analysis, which argues that AI-generated outputs may resemble human creativity, but the underlying mental processes remain distinct—potentially affecting skill development and idea diversity. ADVERTISEMENT Economically, AI is transforming R&D structures and workflows. The 2025 Innovation Barometer finds that 85 percent of firms have redesigned innovation teams to include AI, enabling automation of mundane tasks and fostering cross‑functional integration. More than half of large organisations report that predictive analytics and data processing now dominate team responsibilities, freeing human labour for strategic and creative endeavours. Yet alongside progress, leaders and policymakers emphasise caution. Daniel Kokotajlo warns of runaway scenarios where AI self‑improvement could spark an 'intelligence explosion' by 2027, prompting geopolitical and regulatory urgency. Meta's Yann LeCun notes current systems lack genuine physical-world understanding—a bottleneck that must be overcome in the next five years for true autonomy in robots and vehicles. Ethical debates also linger: as AI undertakes more complex cognitive roles, transparency, fairness and accountability remain central to trust and legitimacy. Industry voices are similarly divided on labour implications. Anthropic's chief, Dario Amodei, cautions that up to half of entry‑level white‑collar roles could vanish within five years, requiring urgent preparedness. Conversely, Nvidia's Jensen Huang, Google's Demis Hassabis and Meta's LeCun predict transformation rather than obsolescence, stressing that human roles will evolve in tandem with AI systems. Innovators such as Ashok Goel and Hannah Davis explore these frontiers from a human-centred perspective. Goel's work at Georgia Tech probes AI's role in cognitive design and creativity. Davis, through generative art and emotion-to-music research, highlights the intersection of AI, bias and cultural context, underscoring that datasets reflect worldviews. AI's transformational impact on research and creativity is multifaceted. Models now support decision-making, accelerate discovery, reshape working practices and challenge cultural norms. To realise human–machine potential, experts urge balanced integration—where ethical guardrails, human oversight and equitable structures underpin technological progress.
